An improved binarization algorithm of wood image defect segmentation based on non-uniform background

Abstract

In this study, an image binarization optimization algorithm, based on local threshold algorithms, is proposed because global and traditional local threshold segmentation algorithms cannot effectively address the problems of non-uniform backgrounds of wood defect images. The proposed algorithm calculates the threshold by the mean, standard deviation and the extreme value of the window. The results indicate that this modified algorithm enhances the image segmentation for wood defect images on a complex background, which is much superior to the global threshold algorithm and the Bernsen algorithm, and slightly better than the Niblack algorithm and Sauvola algorithm. Compared with similar models, the algorithm proposed in this paper has higher segmentation accuracy, as high as 92.6% for wood defect images with a complex background.

Keywords

Non-uniform background / Image segmentation / Binarization / Local threshold / Wood defect

References

[1] Aja-Fernández S, Curiale AH, Vegas-Sánchez-Ferrero G. A local fuzzy thresholding methodology for multi-region image segmentation. Knowl-Based Syst, 2015, 83(1): 1-12.

[2] Cetiner I, Var AA, Cetiner H (2014) Wood surface analysis with image processing techniques. In: Signal processing & communications applications conference

[3] Dalida JPD, Galiza AJN, Godoy AGO, Nakaegawa MQ, Vallester JLM, Cruz ARD (2017) Development of intelligent transportation system for Philippine license plate recognition. In: IEEE Region 10 conference

[4] Dong W, Li H, Wei X, Wang X. An efficient iterative thresholding method for image segmentation. J Comput Phy, 2017, 350: 657-667.

[5] Elyounsi A, Tlijani H, Bouhlel MS (2017) Combining top-hat, thresholding and watershed transformation for 3D inverse synthetic aperture radar images segmentation. In: International conference on sciences of electronics

[6] Gu IYH, Andersson H, Vicen R. Bolc L, Kulikowski JL, Wojciechowski K. Automatic classification of wood defects using support vector machines. Computer vision and graphics. ICCVG 2008, 2008, Berlin: Springer 356 367

[7] Guo J, Liu XY, Wu B, Fu XW. A binarization method for uneven illumination images. Comput Appl Softw, 2014, 31(03): 183-186.

[8] Hittawe MM, Muddamsetty SM, Sidibe D, Meriaudeau F (2015) Multiple features extraction for timber defects detection and classification using SVM. In: IEEE international conference on image processing

[9] Hu R, Odobez JM, Gatica-Perez D. Extracting Maya Glyphs from degraded ancient documents via image segmentation. J Comput Cult Herit (JOCCH), 2017 10 2 10

[10] Jin HE, Liu TG, Zhang H, Zhang ZC. Adaptive algorithm based on morphological top-hat transformation to segment Chinese square seals in bank checks. Opt Precis Eng, 2009, 17(10): 2576-2585.

[11] Liu, S (2013) Research for binarization of uneven illumination text image. In: Proceedings of SPIE—The international society for optical engineering, vol 8768(2), 87686O–87686O-5

[12] Liu S, Zhang L, Zhang Z, Wang C, Xiao B. Automatic cloud detection for all-sky images using superpixel segmentation. IEEE Geosci Remote Sens Lett, 2015, 12(2): 354-358.

[13] Lu R, Dong Y (2016) Component surface defect detection based on image segmentation method. In: Control decision conference

[14] Ma WK, Wang L, He H. Local threshold segmentation algorithm for fingerprint images. Comput Eng Appl, 2009, 45(34): 177-179.

[15] Mostafa A, Elfattah MA, Fouad A, Hassanien AE, Hefny H (2016) Wolf local thresholding approach for liver image segmentation in CT images. In: Proceedings of the second international Afro-European conference for industrial advancement AECIA 2015

[16] Najafi MH, Salehi ME. A fast fault-tolerant architecture for Sauvola local image thresholding algorithm using stochastic computing. IEEE Trans Very Large Scale Integr Syst, 2016, 24(2): 808-812.

[17] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern, 2007, 9(1): 62-66.

[18] Ouyang Q. Uneven illumination license plate image binarization. J Wuhan Univ: Eng Ed, 2006, 39(4): 143-146.

[19] Samorodova OA, Samorodov AV. Fast implementation of the niblack binarization algorithm for microscope image segmentation. Pattern Recognit Image Anal, 2016, 26(3): 548-551.

[20] Senthilkumaran N, Vaithegi S. Image segmentation by using thresholding techniques for medical images. Comput Sci Eng, 2016, 6(1): 1-13.

[21] Shu A, Ruan Q (2017) 3D facial expression recognition algorithm using local threshold binary pattern and histogram of oriented gradient. In: IEEE international conference on signal processing

[22] Vala MHJ, Baxi A. A review on Otsu image segmentation algorithm. Int J Adv Res Comput Eng Technol (IJARCET), 2013 2 2 387

[23] Vijayan G, Reshma SR, Dhanya FE, Anju S, Nair GR, Aneesh RP (2017) A novel shadow removal algorithm using Niblack segmentation in satellite images. In: International conference on communication systems & networks

[24] Vo GD, Park C. Robust regression for image binarization under heavy noise and nonuniform background. Pattern Recognit, 2018, 81: 224-239.

[25] Yi W, Wang J, Sun X, Ming H (2010) A modified Otsu image segment method based on the Rayleigh distribution. In: IEEE international conference on computer science & information technology

[26] Yu L. Study on automatic threshold selection algorithm of sensor images. Phys Procedia, 2012, 25: 1769-1775.

[27] Zhang Y. License plate binarization algorithm based on analysis of the spatial distribution and maximum variance between clusters. J Zhejiang Univ, 2001, 2001(03): 42-45 + 50.

[28] Zheng X, Wei T, Du J (2011) A fast adaptive binarization method based on sub block OSTU and improved sauvola. In: International conference on wireless communications